CN112380982A - Integrated monitoring method for progress and quality of infrastructure project in power industry - Google Patents
Integrated monitoring method for progress and quality of infrastructure project in power industry Download PDFInfo
- Publication number
- CN112380982A CN112380982A CN202011265162.XA CN202011265162A CN112380982A CN 112380982 A CN112380982 A CN 112380982A CN 202011265162 A CN202011265162 A CN 202011265162A CN 112380982 A CN112380982 A CN 112380982A
- Authority
- CN
- China
- Prior art keywords
- progress
- quality
- image
- project
- infrastructure
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063116—Schedule adjustment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Development Economics (AREA)
- Multimedia (AREA)
- Educational Administration (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an integrated monitoring method for progress and quality of a capital construction project in the power industry in the technical field of power construction monitoring, and the technical scheme of the integrated monitoring method is that a deep reinforcement learning model based on a convolutional neural network is adopted, a large amount of image data is collected through an image monitoring device, a power capital construction project is used as a learning sample, then targets such as personnel, equipment, field construction contours and the like in image pictures are extracted through the convolutional neural network, and the progress and quality conditions of the project are integrally monitored by combining a deep reinforcement learning algorithm; the convolutional neural network has the characteristic learning capability, can perform translation and rotation invariant classification on input image information according to the hierarchical structure of the convolutional neural network, effectively extracts an image target, and realizes real-time monitoring on the target.
Description
Technical Field
The invention relates to the technical field of electric power construction monitoring, in particular to an integrated monitoring method for progress and quality of a capital construction project in the electric power industry.
Background
The deep integration of digital economy and industry is a great trend of economic development in the 21 st century in China. The power infrastructure industry also faces the urgent need for a new digital model, new infrastructure, transformation. The digital transformation of the electric power construction site based on data driving as the core is the foundation of successful transformation of electric power infrastructure enterprises in China. However, the electric power construction site infrastructure monitoring method mainly adopts manual data collection and manual monitoring management as a core, and part of simple operation scenes are identified by an intelligent technology, such as whether the electric power construction site enters a forbidden area, wearing a safety helmet, smoking violations and the like. Obviously, the conventional methods have lagged behind the requirements of the times and mainly have the following problems: infrastructure personnel and equipment configuration cannot be monitored on site in real time; the infrastructure progress and quality cannot be monitored in real time. This is likely to cause problems of progress and quality of infrastructure to be discovered only when the predetermined period reaches the end of the project.
Therefore, for the current situation that the on-site construction progress and quality cannot be monitored and analyzed in real time due to the lack of advanced informatization technology in the whole power infrastructure industry, the real-time monitoring of construction site personnel and equipment by using the big data technology becomes the primary choice of each related enterprise. Compared with the traditional infrastructure monitoring method, the digital infrastructure monitoring is realized by combining big data analysis, an artificial intelligence technology and construction site management by using an informatization technology method, and performing data analysis on scattered information of a construction site to monitor the progress of personnel, equipment and projects of the construction site, so that basis and guarantee are provided for high-quality ordered promotion of infrastructure projects.
The first technical scheme is as follows: intelligent management system and method for electric power construction site
Intelligent management system and method at [ invention authorization ] electric power construction site-201710749778.6; 107632565A, the invention provides an intelligent management system and method for an electric power construction site, which collects field environment information through an environment information collection unit arranged on the electric power construction site, and identifies an alarm event according to the field environment information through a processing unit, wherein the alarm event is of a type including: the event that the person enters the electrified forbidden zone illegally, the event that the field person does not wear a safety helmet, the event that the field person ascends the height and does not wear a safety belt and the event that the field person smokes illegally are one or more of; therefore, the intelligent automatic monitoring system realizes intelligent automatic monitoring and alarm event identification of the construction site and solves the problems in the prior art.
In the first scheme, only specific simple warning matters are intelligently monitored, and the method can only intelligently monitor independent events, so that monitoring tasks with a certain time span, such as project progress and quality, can not be identified to be in accordance with the current plan.
The second prior art scheme is: capital construction power transmission project progress monitoring method and monitoring system
Method for project progress monitoring discovery at [ invention authorization ] -201910791590.7; 110505452A, the invention relates to the technical field of electric power construction, the method comprises: acquiring the field image data of each node; establishing an engineering image model corresponding to the capital construction power transmission engineering, wherein the engineering image model comprises a plurality of areas to be filled, which correspond to the nodes one by one; and filling corresponding construction progress information into the area to be filled corresponding to the node according to the on-site image data of each node. The method realizes automatic monitoring of the construction progress of each node of the infrastructure power transmission project, and has the advantages of high efficiency, high accuracy, high updating speed and the like.
And a second scheme is used for establishing an engineering image model, and judging the construction progress by comparing the difference between the current image and the target image. The method can not be considered, and in the construction process, whether the key factors such as personnel configuration, equipment and materials are reasonable or not and whether the progress is in a working condition or not can not be intelligently judged, so that the construction quality problem can not be intelligently judged
Based on the above, the invention designs an integrated monitoring method for the progress and quality of the infrastructure project in the power industry, so as to solve the problems.
Disclosure of Invention
The invention aims to provide an integrated monitoring method for progress and quality of a capital construction project in the power industry, so as to solve the technical problem.
In order to realize the purpose, the invention provides the following technical scheme: an integrated monitoring method for progress and quality of a power industry infrastructure project comprises the following steps:
step S10: preprocessing image data; the method comprises the following steps of preprocessing an original video image from two aspects of enhancement and denoising, and improving the contrast of the indoor and outdoor video images;
step S20: labeling image data; taking a video monitoring image of an electric power infrastructure project as a learning sample, arranging the keyframe images preprocessed in the step S10 in a time sequence, segmenting, carrying out rule matching labeling and artificial labeling, and generating basic sample data of a depth-enhanced learning model based on a convolutional neural network;
step S30: training a deep reinforcement learning model based on a convolutional neural network; training the data processed in the step S20 by adopting a deep reinforcement learning model based on a convolutional neural network to form a project progress and quality integrated identification model based on a deep neural network model; then, the model monitors the project progress and quality condition in the new image data after collecting the real-time image data of the electric power new foundation project and processing the real-time image data in the step S10;
step S40: integrally identifying the infrastructure progress and quality; acquiring image monitoring data of a infrastructure site in real time, preprocessing new image data in the step 1 and extracting key frames, inputting the key frames arranged according to a time sequence into a trained recognition model, automatically acquiring recognition results of infrastructure progress and quality, and particularly early warning a driving phenomenon;
step S50: sample expansion; and (5) manually confirming and checking the model discrimination result of the step (S30), and then expanding the manually discriminated sample data into a sample database, optimizing the model parameters and improving the monitoring performance of the model.
Preferably, in step S10, the original video image processing method specifically includes reading a video and extracting frames, and then performing image preprocessing such as digitization, geometric transformation, normalization, smoothing, restoration, and enhancement.
Preferably, in step S20, the key frame image extraction rule is to use a regular expression to quickly label the sample data according to the content of the acceptance report at each stage of the project, and the manual labeling is used to label the personnel, equipment and site construction contour condition in the construction picture.
Compared with the prior art, the invention has the beneficial effects that:
according to the technical scheme, a deep reinforcement learning model based on a convolutional neural network is adopted, a large amount of image data is collected through an image monitoring device, an electric power capital construction project is used as a learning sample, then targets such as personnel, equipment and field construction outlines in image pictures are extracted through the convolutional neural network, and the conditions of project progress and quality are monitored integrally by combining a deep reinforcement learning algorithm; the convolutional neural network has the characteristic learning capacity, can carry out translation and rotation invariant classification on input image information according to the hierarchical structure of the convolutional neural network, effectively extracts an image target and realizes real-time monitoring on the target.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of an integrated monitoring method for progress and quality of a capital construction project in the power industry.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without any inventive step, are within the scope of the invention.
Referring to fig. 1, the present invention provides a method for integrally monitoring progress and quality of a capital construction project in the power industry, including:
step S10: preprocessing image data; the method comprises the following steps of preprocessing an original video image from two aspects of enhancement and denoising, and improving the contrast of the indoor and outdoor video images;
specifically, in the environment such as rainy days, foggy days, cloudy days, backlight, underexposure, night and the like, the definition of the image can be greatly reduced, and various noises of the photoelectric sensor can also influence the accurate acquisition of the image information. The image data preprocessing aims at efficiently improving the contrast of indoor and outdoor video images and reducing the influence of noise. Therefore, the image data preprocessing is to preprocess the original video image from two aspects of enhancement and denoising; the original video image processing method specifically comprises the steps of reading a video, extracting frames, and then carrying out image preprocessing such as digitalization, geometric transformation, normalization, smoothing, restoration, enhancement and the like.
In the aspect of video enhancement, scene classification and detail preservation are combined on the basis of histogram equalization, and segmented detail preservation histogram equalization processing is performed according to the scene characteristics of an image. The problems of detail loss and brightness saturation of the traditional histogram equalization are avoided, and the method is suitable for the steady processing effect of different infrastructure scenes.
In the aspect of video denoising, a fast non-local mean algorithm is taken as a basis. By utilizing the invariance of the background in applications such as monitoring and the like, the picture is divided into two parts of the background and the motion area to be denoised respectively, the action area of a non-local mean value algorithm is reduced, and the real-time denoising aiming at the video monitoring image is completed.
Step S20: labeling image data; taking a video monitoring image of an electric power infrastructure project as a learning sample, arranging the keyframe images preprocessed in the step S10 in a time sequence, segmenting, carrying out rule matching labeling and artificial labeling, and generating basic sample data of a depth-enhanced learning model based on a convolutional neural network;
specifically, all video monitoring images of an electric power infrastructure project are used as a learning sample, preprocessing of the step 1 is performed on image data, and then the key frames are extracted by adopting a video dynamic and static mixed key frame extraction method. The key frame comprises extracting a background frame and a foreground frame from an original video, counting the number of motion elements, dividing the foreground frame into a static frame and a motion frame, and numbering according to a time sequence.
And (4) segmenting the preprocessed key frame, and adopting different segmentation methods according to different image objects. And (3) segmenting static background objects and people by adopting a 2D boundary frame, segmenting capital construction equipment and a specific construction area by adopting a polygonal boundary frame, and carrying out rule matching annotation and manual annotation on the segmented areas. And the rule matching and marking is to quickly mark sample data by using a regular expression according to the content of the acceptance report at each stage of the project, and the manual marking is used for marking the conditions of personnel, equipment and on-site construction outlines in the construction pictures.
Step S30: training a deep reinforcement learning model based on a convolutional neural network; training the data processed in the step S20 by adopting a deep reinforcement learning model based on a convolutional neural network to form a project progress and quality integrated identification model based on a deep neural network model; then, the model monitors the project progress and quality condition in the new image data after collecting the real-time image data of the electric power new foundation project and processing the real-time image data in the step S10;
specifically, a large amount of electric power infrastructure sample data processed in the step 2 is divided into training samples and testing samples according to a ratio of 9 to 1. Performing model training on a training sample by adopting a deep reinforcement learning model based on a convolutional neural network; the convolutional neural network of the model has the characteristic learning capability and can effectively extract picture objects such as personnel, equipment, construction outlines and the like. The deep reinforcement learning algorithm can comprehensively learn the influence factors of the related objects of the power infrastructure and integrally judge the progress and quality conditions of the current infrastructure image; the test sample is used for checking the reasonableness and effectiveness of object extraction of the electric power infrastructure image and parameter training of the model.
Step S40: integrally identifying the infrastructure progress and quality; acquiring image monitoring data of a infrastructure site in real time, preprocessing new image data in the step 1 and extracting key frames, inputting the key frames arranged according to a time sequence into a trained recognition model, automatically acquiring recognition results of infrastructure progress and quality, and particularly early warning a driving phenomenon;
step S50: sample expansion; and (5) manually confirming and checking the model discrimination result of the step (S30), and then expanding the manually discriminated sample data into a sample database, optimizing the model parameters and improving the monitoring performance of the model.
In the description of the invention, it is to be understood that the terms "coaxial", "bottom", "one end", "top", "middle", "other end", "upper", "one side", "top", "inner", "front", "center", "two ends", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of describing the invention and simplifying the description, but do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the invention.
In the present invention, unless otherwise expressly specified or limited, the terms "mounted," "disposed," "connected," "fixed," "screwed" and the like are to be construed broadly, e.g., as meaning fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; the terms may be directly connected or indirectly connected through an intermediate, and may be communication between two elements or interaction relationship between two elements, unless otherwise specifically defined, and the specific meaning of the above terms in the present invention will be understood by those skilled in the art according to specific situations.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (3)
1. An integrated monitoring method for progress and quality of a capital construction project in the power industry is characterized in that:
step S10: preprocessing image data; the method comprises the following steps of preprocessing an original video image from two aspects of enhancement and denoising, and improving the contrast of the indoor and outdoor video images;
step S20: labeling image data; taking a video monitoring image of an electric power infrastructure project as a learning sample, arranging the keyframe images preprocessed in the step S10 in a time sequence, segmenting, carrying out rule matching labeling and artificial labeling, and generating basic sample data of a depth-enhanced learning model based on a convolutional neural network;
step S30: training a deep reinforcement learning model based on a convolutional neural network; training the data processed in the step S20 by adopting a deep reinforcement learning model based on a convolutional neural network to form a project progress and quality integrated identification model based on a deep neural network model; then, after collecting real-time image data of the new electric power infrastructure project and processing the real-time image data in the step S10, monitoring project progress and quality conditions in the new image data by the model;
step S40: integrally identifying the infrastructure progress and quality; acquiring image monitoring data of a infrastructure site in real time, preprocessing new image data in the step 1 and extracting key frames, inputting the key frames arranged according to a time sequence into a trained recognition model, automatically acquiring recognition results of infrastructure progress and quality, and particularly early warning a driving phenomenon;
step S50: sample expansion; and (5) manually confirming and checking the model discrimination result of the step (S30), and then expanding the manually discriminated sample data into a sample database, optimizing the model parameters and improving the monitoring performance of the model.
2. The integrated monitoring method for progress and quality of an electric power industry infrastructure project according to claim 1, characterized in that: in step S10, the original video image processing method specifically includes reading a video and extracting frames, and then performing image preprocessing such as digitization, geometric transformation, normalization, smoothing, restoration, enhancement, and the like.
3. The integrated monitoring method for progress and quality of an electric power industry infrastructure project according to claim 1, characterized in that: in the step S20, the key frame image extraction rule is to use a regular expression to quickly label sample data according to the content of the acceptance report at each stage of the project, and the manual labeling is used to label the personnel, equipment and site construction contour condition in the construction picture.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011265162.XA CN112380982A (en) | 2020-11-13 | 2020-11-13 | Integrated monitoring method for progress and quality of infrastructure project in power industry |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011265162.XA CN112380982A (en) | 2020-11-13 | 2020-11-13 | Integrated monitoring method for progress and quality of infrastructure project in power industry |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112380982A true CN112380982A (en) | 2021-02-19 |
Family
ID=74583615
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011265162.XA Pending CN112380982A (en) | 2020-11-13 | 2020-11-13 | Integrated monitoring method for progress and quality of infrastructure project in power industry |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112380982A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113111825A (en) * | 2021-04-22 | 2021-07-13 | 北京房江湖科技有限公司 | Construction monitoring method and device, electronic equipment and storage medium |
| CN113269233A (en) * | 2021-04-29 | 2021-08-17 | 国网福建省电力有限公司 | Intelligent monitoring and early warning system and method for subcontracting and subcontracting of building engineering |
| CN113379324A (en) * | 2021-07-06 | 2021-09-10 | 山东电力工程咨询院有限公司 | Construction site whole-course monitoring method and system |
| CN113949933A (en) * | 2021-09-30 | 2022-01-18 | 卓尔智联(武汉)研究院有限公司 | Playing data analysis method, device, equipment and storage medium |
| CN115115881A (en) * | 2022-06-28 | 2022-09-27 | 重庆大学 | Gastroscope image representation learning method utilizing medical examination report |
| CN116681320A (en) * | 2023-04-07 | 2023-09-01 | 中宬建设管理有限公司 | Engineering monitoring integrated intelligent management method and system |
| CN117273440A (en) * | 2023-09-01 | 2023-12-22 | 西华大学 | Engineering construction Internet of things monitoring and managing system and method based on deep learning |
| CN117634864A (en) * | 2024-01-24 | 2024-03-01 | 华仁建设集团有限公司 | Intelligent construction task optimization method and system based on image analysis |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108174165A (en) * | 2018-01-17 | 2018-06-15 | 重庆览辉信息技术有限公司 | Electric power safety operation and O＆M intelligent monitoring system and method |
| CN109784622A (en) * | 2018-12-10 | 2019-05-21 | 国网湖北省电力有限公司 | Power grid project process monitoring method and system based on geographical wiring diagram |
| CN110505452A (en) * | 2019-08-26 | 2019-11-26 | 广东电网有限责任公司 | A kind of capital construction power transmission engineering Schedule monitoring method and monitoring system |
| CN110956285A (en) * | 2019-11-25 | 2020-04-03 | 科大国创软件股份有限公司 | Deep learning-based assembly and maintenance construction normative detection method and system |
-
2020
- 2020-11-13 CN CN202011265162.XA patent/CN112380982A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108174165A (en) * | 2018-01-17 | 2018-06-15 | 重庆览辉信息技术有限公司 | Electric power safety operation and O＆M intelligent monitoring system and method |
| CN109784622A (en) * | 2018-12-10 | 2019-05-21 | 国网湖北省电力有限公司 | Power grid project process monitoring method and system based on geographical wiring diagram |
| CN110505452A (en) * | 2019-08-26 | 2019-11-26 | 广东电网有限责任公司 | A kind of capital construction power transmission engineering Schedule monitoring method and monitoring system |
| CN110956285A (en) * | 2019-11-25 | 2020-04-03 | 科大国创软件股份有限公司 | Deep learning-based assembly and maintenance construction normative detection method and system |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113111825A (en) * | 2021-04-22 | 2021-07-13 | 北京房江湖科技有限公司 | Construction monitoring method and device, electronic equipment and storage medium |
| CN113269233A (en) * | 2021-04-29 | 2021-08-17 | 国网福建省电力有限公司 | Intelligent monitoring and early warning system and method for subcontracting and subcontracting of building engineering |
| CN113379324A (en) * | 2021-07-06 | 2021-09-10 | 山东电力工程咨询院有限公司 | Construction site whole-course monitoring method and system |
| CN113949933A (en) * | 2021-09-30 | 2022-01-18 | 卓尔智联(武汉)研究院有限公司 | Playing data analysis method, device, equipment and storage medium |
| CN113949933B (en) * | 2021-09-30 | 2023-08-22 | 卓尔智联(武汉)研究院有限公司 | Playing data analysis method, device, equipment and storage medium |
| CN115115881A (en) * | 2022-06-28 | 2022-09-27 | 重庆大学 | Gastroscope image representation learning method utilizing medical examination report |
| CN116681320A (en) * | 2023-04-07 | 2023-09-01 | 中宬建设管理有限公司 | Engineering monitoring integrated intelligent management method and system |
| CN116681320B (en) * | 2023-04-07 | 2023-12-05 | 中宬建设管理有限公司 | Engineering monitoring integrated intelligent management method and system |
| CN117273440A (en) * | 2023-09-01 | 2023-12-22 | 西华大学 | Engineering construction Internet of things monitoring and managing system and method based on deep learning |
| CN117634864A (en) * | 2024-01-24 | 2024-03-01 | 华仁建设集团有限公司 | Intelligent construction task optimization method and system based on image analysis |
| CN117634864B (en) * | 2024-01-24 | 2024-04-05 | 华仁建设集团有限公司 | Intelligent construction task optimization method and system based on image analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112380982A (en) | Integrated monitoring method for progress and quality of infrastructure project in power industry | |
| CN110738127A (en) | Helmet identification method based on unsupervised deep learning neural network algorithm | |
| CN106610969A (en) | Multimodal information-based video content auditing system and method | |
| CN111832398B (en) | Unmanned aerial vehicle image distribution line pole tower ground wire broken strand image detection method | |
| CN104504377B (en) | A kind of passenger on public transport degree of crowding identifying system and method | |
| CN111339883A (en) | Method for identifying and detecting abnormal behaviors in transformer substation based on artificial intelligence in complex scene | |
| CN102915432A (en) | Method and device for extracting vehicle-bone microcomputer image video data | |
| CN110096945B (en) | Indoor monitoring video key frame real-time extraction method based on machine learning | |
| CN112464893A (en) | Congestion degree classification method in complex environment | |
| CN101051344B (en) | Sensitive video frequency identifying method based on light stream direction histogram and skin color stream form variation | |
| CN113469938B (en) | Pipe gallery video analysis method and system based on embedded front-end processing server | |
| CN111897993A (en) | Efficient target person track generation method based on pedestrian re-recognition | |
| CN117576632B (en) | Multi-mode AI large model-based power grid monitoring fire early warning system and method | |
| Yang et al. | PDNet: Improved YOLOv5 nondeformable disease detection network for asphalt pavement | |
| CN111339927A (en) | Intelligent work state identification system for personnel in electric power business hall | |
| CN105354591B (en) | Three-dimensional outdoor scene semantic segmentation system based on high-order classification correlation priori knowledge | |
| CN202815869U (en) | Vehicle microcomputer image and video data extraction apparatus | |
| CN113269233A (en) | Intelligent monitoring and early warning system and method for subcontracting and subcontracting of building engineering | |
| CN117119253B (en) | High-quality video frame extraction method for target object | |
| CN112907734A (en) | TEDS fault detection method based on virtual CRH380A model and deep learning | |
| CN112258552A (en) | Pedestrian multi-target tracking method under community monitoring scene | |
| CN107707975A (en) | Video intelligent clipping method based on monitor supervision platform | |
| CN116052110A (en) | Intelligent positioning method and system for pavement marking defects | |
| CN115439690A (en) | Flue-cured tobacco leaf image grading method combining CNN and Transformer | |
| CN112686105B (en) | Fog concentration grade identification method based on video image multi-feature fusion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |